© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 24026
    Prev
    Next
    INDEX
    Explanations

    adverbs emphasizing the speaker's feelings or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong personal opinion or sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     damaging
    -0.61
    Creat
    -0.60
     influencing
    -0.59
     Trap
    -0.59
     populous
    -0.58
     Harding
    -0.58
     Binding
    -0.57
     causing
    -0.56
     guiActiveUnfocused
    -0.56
     Trend
    -0.55
    POSITIVE LOGITS
     wish
    1.21
     recommend
    1.16
     believe
    1.15
     intend
    1.09
     owe
    1.09
     regret
    1.08
     appreciate
    1.07
     adore
    1.05
     prefer
    1.05
     think
    1.05
    Activations Density 0.126%

    No Known Activations